phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-28 02:31:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: enable pyupgrade fixes

Browse source 
Schema reflection code needed a minor adjustment to handle UnionTypes
and collections.abc.AsyncIterator. (Both are preferred for latest Python
releases.)

Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
This commit is contained in:
Ihar Hrachyshka 2025-03-26 18:33:23 -04:00
parent ffe3d0b2cd
commit 1deb95f922
319 changed files with 2843 additions and 3033 deletions
Download patch file Download diff file Expand all files Collapse all files

13
llama_stack/models/llama/llama3/args.py
View file

@ -6,7 +6,6 @@
from dataclasses import dataclass
from enum import Enum
from typing import Optional
class QuantizationScheme(Enum):
@ -15,8 +14,8 @@ class QuantizationScheme(Enum):
@dataclass
class QuantizationArgs:
scheme: Optional[QuantizationScheme] = None
group_size: Optional[int] = None
scheme: QuantizationScheme | None = None
group_size: int | None = None
spinquant: bool = False
def __init__(self, **kwargs):
@ -39,10 +38,10 @@ class ModelArgs:
dim: int = 4096
n_layers: int = 32
n_heads: int = 32
n_kv_heads: Optional[int] = None
n_kv_heads: int | None = None
vocab_size: int = -1
multiple_of: int = 256 # make SwiGLU hidden layer size multiple of large power of 2
ffn_dim_multiplier: Optional[float] = None
ffn_dim_multiplier: float | None = None
norm_eps: float = 1e-5
rope_theta: float = 500000
use_scaled_rope: bool = False
@ -55,8 +54,8 @@ class ModelArgs:
vision_max_num_chunks: int = 4
vision_num_cross_attention_layers: int = -1
quantization_args: Optional[QuantizationArgs] = None
lora_args: Optional[LoRAArgs] = None
quantization_args: QuantizationArgs | None = None
lora_args: LoRAArgs | None = None
def __init__(self, **kwargs):
for k, v in kwargs.items():